NC Bench
Overview
About
Tests
Models
Model
GPT-4.1
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-04-14-01JRTSTD0S8EHVJAAJS94DM15N
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
“Molly, you realize we’re about to rob a bunch of kids, right?” “Bill, it’s not robbery if they never see us. It’s creative redistribution.” “Redistribution of toys. Plush bunnies, probably. Maybe a Lego set.” “Lego sets are worth their weight in microchips, Bill. You want to retire early or don’t you?” “I was hoping to retire with my dignity. Not with a sack of Princess Sparkle dolls.” “Trust me, some of those dolls are collectibles. Limited edition’s practically currency.” “Then explain why you’ve got clown makeup in your bag.” “Disguise, obviously. No one suspects the clown. Children love clowns.” “Children fear clowns, Molly. Even I fear clowns. Besides, what’s my role?” “You’re the magician. You distract the crowd, do some card tricks, I sneak behind the cake and grab the loot.” “I don’t even know card tricks. Last time I tried, your cat ran off with the ace of spades.” “Just keep shuffling, Bill. Kids don’t know real magic from a nervous breakdown.” “Fine, say we actually pull this off. Where do we stash the loot?” “We borrow a stroller. Hide everything under a mountain of balloons. Walk out smiling.” “You know what, Molly? I definitely need a raise.”
id
"gen-1744656217-GdtdlBcwTqyP0gX2wQVy"
upstream_id
"chatcmpl-BMJ4Ljp37QRvsFdQ4AopIkHBpXzcr"
total_cost
0.002358
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:43:41.564953+00:00"
Monday, April 14th, 2025 at 6:43:41 PM GMT+00:00
model
"openai/gpt-4.1-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
385
moderation_latency
148
generation_time
3174
tokens_prompt
68
tokens_completion
277
native_tokens_prompt
67
native_tokens_completion
278
native_tokens_reasoning
0
num_media_prompt
(null)
num_media_completion
(null)
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.002358
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
199
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
199
wordsDialogue
199
68.3935%